Platform
GA
Proprietary
DeepInfra
Low-cost serverless inference for open models
Release2022-01
Context—
Max output—
ParametersUndisclosed
Local / VRAMAPI only
LicenseProprietary
Overview
DeepInfra is a model in the Platform category from DeepInfra. It was released in 2022-01. The vendor is based in US. Best for: Low-cost serverless inference for open models.
Notes: Positioning from the vendor site; specs, access and pricing can change — verify before production use.
Strengths
- Low token prices
- OpenAI-compatible
Limits
- Fewer enterprise features
- Catalog varies
Specifications
| Vendor | DeepInfra |
|---|---|
| Category | Platform |
| Release | 2022-01 |
| Status | GA |
| License | Proprietary |
| Commercial use | Not specified |
| Input modalities | Text |
| Output modalities | Text |
| Prompt types | Text |
| Negative prompts | No |
| Max outputs | 1 |
| Local deployment | No |
| API access | Yes |
| Pricing | Per token |
| Confidence | Medium |
| Vendor country | US |
| Vendor type | Platform |
Pricing & hardware
Per token
API-only: local GPU memory is not applicable. API access is available.